Artificial immune system based wastewater parameter estimation

The basis of a wastewater treatment system is to achieve the desired characteristics of the wastewatertreatment process. An estimation of the obtained wastewater treatment characteristics provides the information neededto set up the current process steps, and it is important to have an optimum treatment. In this study, an artificialimmune system (AIS) structure is developed to estimate important wastewater output parameters such as pH, DBO,DQO, and SS for the first time. The proposed AIS models are based on the clonal selection principle, and the dataset isprovided from the University of California Irvine (UCI) Machine Learning Library. The current dataset is analyzed byprincipal component analysis (PCA) to obtain maximum system performance. As a result of the simulation, the outputparameters are successfully predicted using the AIS model with real data. The classifier’s performance ratios are studiedseparately using the coefficient of determination (R2) and the mean squared error of prediction (MSEP), and their ratesare given in this study

PDF

___

Raha D. Sustainable Management of Wastewater Treatment Plant Using ISO 14001:2004 EMS and Neural Network Modeling. Indian Chem Engr 2005; 47: 182-188.
IUCN/UNEP/WWF. Caring for the earth a strategy for sustainable living. Gland Switzerland, 1991.
Sertkaya C. Atıksu arıtma tesisi kontrolünde yapay bağışıklık sisteminin kullanılması, PhD, Sakarya University, Sakarya, Turkey, 2016 (in Turkish).
Tchobanoglous G, Burton FL, Stensel HD. Wastewater Engineering: Treatment and Reuse. 4th ed. New York, NY, USA: McGraw-Hill, 2002.
Samsunlu A. Atık Suların Arıtılması. İstanbul, Turkey: Birsen Yayınevi, 2011 (in Turkish).
Han H, Qiao J. Nonlinear model-predictive control for industrial processes: an application to wastewater treatment process. IEEE T Ind Electron 2014; 61: 1970-1982.
Liang J, Luo F, Yu R, Xu Y. Wastewater effluent prediction based on fuzzy-rough sets RBF neural networks. In: 2010 Networking, Sensing and Control (ICNSC) Conference; 11–13 April 2010; Chicago USA. pp. 393-397.
Yılmaz EC, Doğan E. Modelling of wastewater treatment plant performance using adaptive neuro fuzzy inference systems. Elec Lett Sci Eng 2008; 4: 1-9.
Subaşı H. Modeling wastewater treatment performance using artificial neural networks. MSc, Adana, Turkey, 2010.
Meenakhsipriya B, Saravanan K, Sathiyavathi S. Neural based pH system in effluent treatment process. Mod Appl Sci 2009; 3: 166.
Riano D. Learning rules within the framework of environmental sciences. ECAI 98-W7 (BESAI98) 1998; 151-165.
MacGregor JF, Kourti T. Statistical process control of multivariable processes. Control Eng Pract 1995; 3: 403-414.
Oliveira-Esquerre KP, Mori M, Bruns RE. Simulation of an industrial wastewater treatment using artificial neural networks and principal components analysis. Braz J Chem Eng 2002; 19: 365-370.
Civelekoğlu G. The modeling of treatment processes with artificial intelligence and multistatistical methods. PhD, Süleyman Demirel University, Isparta, Turkey, 2006.
Everitt BS, Dunn G. Applied Multivariate Data Analysis. 2nd ed. London, UK: Wiley, 2001.
Garrett SM. How do we evaluate artificial immune systems? Evolutionary Computation 2005; 13: 145-178.
Wang H, Peng D, Wang W, Sharif H, Wegiel J, Nguyen D, Bowne R, Backhaus C. Artificial Immune System based image pattern recognition in energy efficient wireless multimedia sensor networks. In: Military Communications Conference 2008; San Diego, USA. pp. 1-7.
Neagoe VE, Neghina CE. An artificial immune system approach for unsupervised pattern recognition in multispectral remote-sensing imagery. In: 2011 Proceedings of the 13th IASME/WSEAS International Conference on Mathematical Methods and Computational Techniques in Electrical Engineering conference on Applied Computing. pp. 228-233.
Harmer PK, Williams PD, Gunsch GH, Lamont GB. An artificial immune system architecture for computer security applications. IEEE T Evolut Comput 2002; 6: 252-280.
Oil CM, Wang YT, Ou CR. Intrusion detection systems adapted from agent-based artificial immune systems. In: IEEE International Conference on Fuzzy Systems; 2011; Taipei, Taiwan. pp. 115-122.
Ou CM. Host-based intrusion detection systems adapted from agent-based artificial immune systems. Neurocomputing 2012; 88: 78-86.
Engin O, Doyen A. A new approach to solve hybrid flow shop scheduling problems by artificial immune system. Future Gener Comp Sy 2004; 20: 1083-1095.
Özşen S, Güneş S. Performance evolution of a newly developed general-use hybrid AIS-ANN system: AaA-response. Turk J Elec Eng & Comp Sci 2013; 21: 1703-1719.
Mousavi M, Bakar AA, Zainudin S, Long ZA, Sahani, M, Vakilian M. Negative selection algorithm for dengue outbreak detection. Turk J Elec Eng & Comp Sci 2013; 21: 2345-2356.
Baygin M, Karakose M. Immunity-based optimal estimation approach for a new real time group elevator dynamic control application for energy and time saving. Sci World J 2013; 2013: 1-12.
Atay Y, Kodaz H. Optimization of job shop scheduling problems using modified clonal selection algorithm. Turk J Elec Eng & Comp Sci 2014; 22: 1528-1539.
Sertkaya C. Immune System in Computer Security. MSc, Institute of Natural Sciences, Sakarya University, Turkey, 2009.
Lefkovits S, Lefkovits L. Distance based k-nn classification of gabor jet local descriptors. Procedia Tech 2015; 19: 780-785.
Saini I, Singh D, Khosla A. QRS detection using k-nearest neighbor algorithm (KNN) and evaluation on standard ECG databases. J Adv Res 2013; 4: 331-344.